language	tags	license	library_name
en	audio automatic-speech-recognition	mit	ctranslate2

Whisper distil-large-v2 model for CTranslate2

This repository contains the conversion of distil-whisper/distil-large-v2 to the CTranslate2 model format.

This model can be used in CTranslate2 or projects based on CTranslate2 such as faster-whisper.

Example

from faster_whisper import WhisperModel

model = WhisperModel("distil-large-v2")

segments, info = model.transcribe("audio.mp3")
for segment in segments:
    print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))

Conversion details

The original model was converted with the following command:

ct2-transformers-converter --model distil-whisper/distil-large-v2 --output_dir faster-distil-whisper-large-v2 \
    --copy_files tokenizer.json preprocessor_config.json --quantization float16

Note that the model weights are saved in FP16. This type can be changed when the model is loaded using the compute_type option in CTranslate2.

More information

For more information about the original model, see its model card.